Path planning method for coal mine inspection robot
-
摘要: 路径规划是巡检机器人自主移动的关键技术。煤矿巡检机器人采用快速扩展随机树（RRT）算法规划路径时存在收敛速度慢、搜索效率低等问题。针对该问题，提出了一种合力势场引导RRT算法：利用合力势场中的斥力场构建动态步长，使煤矿巡检机器人在障碍物附近调整步长，提高算法收敛速度；利用目标节点和随机节点2个方向上的引力场与最近障碍物对煤矿巡检机器人产生的斥力场形成的合力场来改善新节点的生成方向，降低树在扩展时的随机性，提高算法搜索效率。对基于合力势场引导RRT算法规划的路径进行剪枝操作，并利用三阶贝塞尔曲线进行平滑处理。在Matlab软件中对基于合力势场引导RRT算法的煤矿巡检机器人路径规划方法进行仿真实验，结果表明：与RRT算法和RRT*算法相比，简单环境下合力势场引导RRT算法的路径规划时间平均值分别减少了33.84%和44.27%，路径长度平均值分别减少了15.29%和4.42%，复杂环境下路径规划时间平均值分别减少了34.93%和47.12%，路径长度平均值分别减少了13.64%和9.44%，模拟煤矿环境下路径规划时间平均值分别减少了28.06%和42.67%，路径长度平均值分别减少了12.22%和10.18%；对基于合力势场引导RRT算法规划的路径进行剪枝和平滑操作后，路径转折点减少，路径角度变化减小，路径更加平滑。Abstract: Path planning is a key technology for autonomous movement of inspection robot. The coal mine inspection robot has problems such as slow convergence speed and low search efficiency when planning paths using the rapidly-expanding random tree (RRT) algorithm. In order to solve the above problems, a combined force potential field guided RRT algorithm is proposed. The algorithm uses the repulsive force field in the combined force potential field to construct a dynamic step size. The coal mine inspection robot can adjust the step size near obstacles to improve the convergence speed of the algorithm. By utilizing the combined force field formed by the gravitational field in both the target node and random node directions, as well as the repulsive field generated by the nearest obstacle on the coal mine inspection robot, the generation direction of new nodes can be improved. It reduces the randomness of tree expansion and enhances the search efficiency of the algorithm. A pruning operation is performed on the paths planned based on the combined potential field guided RRT algorithm and smoothed using third-order Bessel curve. A simulation experiment is conducted in Matlab software on the path planning method of the coal mine inspection robot guided by the combined force potential field RRT algorithm. The results show that compared with the RRT algorithm and RRT* algorithm, the average path planning time of the combined potential field guided RRT algorithm in simple environments is reduced by 33.84% and 44.27%. The average path length is reduced by 15.29% and 4.42%, respectively. In complex environments, the average path planning time is reduced by 34.93% and 47.12%, and the average path length is reduced by 13.64% and 9.44%, respectively. In simulated coal mine environments, the average path planning time is reduced by 28.06% and 42.67%, and the average path length is reduced by 12.22% and 10.18%, respectively. After pruning and smoothing the path planned by the combined force potential field guided RRT algorithm, the number of turning points and angle changes in the path decrease, making the path smoother.
-
图 1 合力势场引导RRT算法新节点生成
Figure 1. New node generation of combined potential field guided rapidly-expanding random tree(RRT) algorithm
图 3 基于三阶贝塞尔曲线的路径平滑效果
Figure 3. Path smoothing effect based on third-order Bessel curve
图 5 简单环境下3种算法的路径规划结果
Figure 5. Path planning results of three algorithms in a simple environment
图 6 复杂环境下3种算法的路径规划结果
Figure 6. Path planning results of three algorithms in a complex environment
图 7 模拟煤矿环境下3种算法的路径规划结果
Figure 7. Path planning results of three algorithm in simulated coal mine environment
图 8 3种环境下剪枝和平滑前后规划路径对比
Figure 8. Path comparison before and after pruning and smoothing in three environments
表 1 简单环境下3种算法实验指标对比
Table 1. Comparison of experimental indexes of three algorithms in a simple environment
算法 路径规划时间平均值/s 路径长度平均值/mm RRT算法 3.31 1 289.2 RRT*算法 3.93 1 142.6 合力势场引导RRT算法 2.19 1 092.1 
下载: 导出CSV
表 2 复杂环境下3种算法实验指标对比
Table 2. Comparison of experimental indexes of three algorithms in a complex environment
算法 路径规划时间平均值/s 路径长度平均值/mm RRT算法 4.38 1 313.6 RRT*算法 5.39 1 252.6 合力势场引导RRT算法 2.85 1 134.4
下载: 导出CSV
表 3 模拟煤矿环境下3种算法实验指标对比
Table 3. Comparison of experimental indexes of three algorithms in simulated coal mine environment
算法 路径规划时间平均值/s 路径长度平均值/mm RRT算法 3.10 1 324.2 RRT*算法 3.89 1 294.2 合力势场引导RRT算法 2.23 1 162.4
下载: 导出CSV
表 4 3种环境下剪枝和平滑前后规划路径的角度变化平均值
Table 4. Mean values of angular change before and after path pruning and smoothing in three environments
仿真环境 路径角度变化平均值/（°） 剪枝和平滑前 剪枝和平滑后 简单环境 32.87 10.67 复杂环境 21.50 10.06 模拟煤矿环境 16.86 6.56
下载: 导出CSV
-
[1] 蔡治华,周东旭,赵明辉. 煤矿巡检机器人控制系统设计[J]. 工矿自动化,2022,48(5):112-117.CAI Zhihua,ZHOU Dongxu,ZHAO Minghui. Design of coal mine inspection robot control system[J]. Journal of Mine Automation,2022,48(5):112-117. [2] 姜媛媛,丰雪艳. 基于改进A*算法的煤矿救援机器人路径规划[J]. 工矿自动化,2023,49(8):53-59.JIANG Yuanyuan,FENG Xueyan. Path planning of coal mine rescue robot based on improved A* algorithm[J]. Journal of Mine Automation,2023,49(8):53-59. [3] 李薪颖,单梁,常路,等. 复杂环境下基于多目标粒子群的DWA路径规划算法[J]. 国防科技大学学报,2022,44(4):52-59. doi: 10.11887/j.cn.202204006LI Xinying,SHAN Liang,CHANG Lu,et al. DWA path planning algorithm based on multi-objective particle swarm optimization in complex environment[J]. Journal of National University of Defense Technology,2022,44(4):52-59. doi: 10.11887/j.cn.202204006 [4] ZHANG Yinyan,LI Shuai,GUO Hongliang. A type of biased consen sus-based distributed neural network for path planning[J]. Nonlinear Dynamics,2017,89:1803-1815. [5] 李波,杨志鹏,贾卓然,等. 一种无监督学习型神经网络的无人机全区域侦察路径规划[J]. 西北工业大学学报,2021,39(1):77-84. doi: 10.3969/j.issn.1000-2758.2021.01.010LI Bo,YANG Zhipeng,JIA Zhuoran,et al. An unsupervised learning neural network for planning UAV full-area reconnaissance path[J]. Journal of Northwestern Polytechnical University,2021,39(1):77-84. doi: 10.3969/j.issn.1000-2758.2021.01.010 [6] OROZCO-ROSAS U,OSCAR M,SEPULVEDA R. Mobile robot path planning using membrane evolutionary artificial potential field[J]. Applied Soft Computing,2019,77:236-251. doi: 10.1016/j.asoc.2019.01.036 [7] 翟丽,张雪莹,张闲,等. 基于势场法的无人车局部动态避障路径规划算法[J]. 北京理工大学学报,2022,42(7):696-705.ZHAI Li,ZHANG Xueying,ZHANG Xian,et al. Local dynamic obstacle avoidance path planning algorithm for unmanned vehicles based on potential field method[J]. Transactions of Beijing Institute of Technology,2022,42(7):696-705. [8] 叶颖诗,魏福义,蔡贤资. 基于并行计算的快速Dijkstra算法研究[J]. 计算机工程与应用,2020,56(6):58-65. doi: 10.3778/j.issn.1002-8331.1903-0119YE Yingshi,WEI Fuyi,CAI Xianzi. Research on fast Dijkstra algorithm based on parallel computing[J]. Computer Engineering and Applications,2020,56(6):58-65. doi: 10.3778/j.issn.1002-8331.1903-0119 [9] 巩慧,倪翠,王朋,等. 基于Dijkstra算法的平滑路径规划方法[J]. 北京航空航天大学学报,2024,50(2):535-541.GONG Hui,NI Cui,WANG Peng,et al. A smooth path planning method based on Dijkstra algorithm[J]. Journal of Beijing University of Aeronautics and Astronautics,2024,50(2):535-541. [10] 刘新宇,谭力铭,杨春曦,等. 未知环境下的蚁群−聚类自适应动态路径规划[J]. 计算机科学与探索,2019,13(5):846-857. doi: 10.3778/j.issn.1673-9418.1811015LIU Xinyu,TAN Liming,YANG Chunxi,et al. Self-adjustable dynamic path planning of unknown environment based on ant colony-clustering algorithm[J]. Journal of Frontiers of Computer Science and Technology,2019,13(5):846-857. doi: 10.3778/j.issn.1673-9418.1811015 [11] 敖邦乾,杨莎,叶振环. 改进蚁群算法水面无人艇平滑路径规划[J]. 控制理论与应用,2021,38(7):1006-1014. doi: 10.7641/CTA.2021.00735AO Bangqian,YANG Sha,YE Zhenhuan. Improved ant colony algorithm for unmanned surface vehicle smooth path planning[J]. Control Theory & Applications,2021,38(7):1006-1014. doi: 10.7641/CTA.2021.00735 [12] ZHANG Haojian,WANG Yunkuan,ZHENG Jun,et al. Path planning of industrial robot based on improved RRT algorithm in complex environments[J]. IEEE Access,2018,6. DOI: 10.1109/access.2018.2871222. [13] LI Binghui,CHEN Badong. An adaptive rapidly-exploring random tree[J]. IEEE/CAA Journal of Automatica Sinica,2021,9(2):283-294. [14] NGUYEN M K,JAILLET L,REDON S. ART-RRT:As-rigid-as-possible exploration of ligand unbinding pathways[J]. Journal of Computational Chemistry Organic Inorganic Physical Biological,2018,39(11):665-678. [15] BRY A,ROY N. Rapidly-exploring random belief trees for motion planning under uncertainty[C]. IEEE International Conference on Robotics and Automation,Shanghai,2011:723-730. [16] QURESHI A H,MUMTAZ S,FAHAD L K,et al. Adaptive potential guided directional-RRT[C]. IEEE International Conference on Robotics & Biomimetics,Shenzhen,2014:1887-1892. [17] 刘成菊,韩俊强,安康. 基于改进RRT算法的RoboCup机器人动态路径规划[J]. 机器人,2017,39(1):8-15.LIU Chengju,HAN Junqiang,AN Kang. Dynamic path planning based on an improved RRT algorithm for RoboCup robot[J]. Robot,2017,39(1):8-15. [18] 司徒华杰,雷海波,庄春刚. 动态环境下基于人工势场引导的RRT路径规划算法[J]. 计算机应用研究,2021,38(3):714-717,724.SITU Huajie,LEI Haibo,ZHUANG Chungang. Artificial potential field based RRT algorithm for path planning in dynamic environment[J]. Application Research of Computers,2021,38(3):714-717,724. [19] 李伟东,李乐. 基于改进RRT算法的无人车路径规划[J]. 计算机测量与控制,2023,31(1):160-166.LI Weidong,LI Le. Path planning of unmanned vehicle based on improved RRT algorithm[J]. Computer Measurement & Control,2023,31(1):160-166. [20] 陈侠,刘奎武,毛海亮. 基于APF−RRT算法的无人机航迹规划[J]. 电光与控制,2022,29(5):17-22. doi: 10.3969/j.issn.1671-637X.2022.05.004CHEN Xia,LIU Kuiwu,MAO Hailiang. UAV path planning based on APF-RRT algorithm[J]. Electronics Optics & Control,2022,29(5):17-22. doi: 10.3969/j.issn.1671-637X.2022.05.004 [21] 王道威,朱明富,刘慧. 动态步长的RRT路径规划算法[J]. 计算机技术与发展,2016,26(3):105-107,112.WANG Daowei,ZHU Mingfu,LIU Hui. Rapidly-exploring random tree algorithm based on dynamic step[J]. Computer Technology and Development,2016,26(3):105-107,112. -
点击查看大图
计量
- 文章访问数: 150
- HTML全文浏览量: 34
- PDF下载量: 30
- 被引次数: 0
